Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5811 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1958. Min Range: -9.1958
Max Act: 9.1958. Min Act: -0.1700
Data Index: 6163799 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1958. Min Range: -9.1958
Max Act: 9.1333. Min Act: -0.1700
Data Index: 1459191 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1958. Min Range: -9.1958
Max Act: 9.0083. Min Act: -0.1700
Data Index: 5100869 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.9458. Min Act: -0.1700
Data Index: 8541896 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1958. Min Range: -9.1958
Max Act: 9.0083. Min Act: -0.1700
Data Index: 4164348 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.9458. Min Act: -0.1700
Data Index: 7402366 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.8833. Min Act: -0.1700
Data Index: 269698 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.9458. Min Act: -0.1700
Data Index: 6163787 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.8833. Min Act: -0.1700
Data Index: 8445331 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.8833. Min Act: -0.1700
Data Index: 105965 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.8833. Min Act: -0.1700
Data Index: 6782080 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.9458. Min Act: -0.1700
Data Index: 5304053 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.9458. Min Act: -0.1700
Data Index: 3646907 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.8208. Min Act: -0.1700
Data Index: 7856495 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.8208. Min Act: -0.1700
Data Index: 4047748 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.8208. Min Act: -0.1700
Data Index: 3395622 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.7583. Min Act: -0.1700
Data Index: 4637235 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.7583. Min Act: -0.1700
Data Index: 387031 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.7583. Min Act: -0.1700
Data Index: 158588 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1958. Min Range: -9.1958
Max Act: 8.7583. Min Act: -0.1700
Data Index: 5044626 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19